Literature DB >> 33738763

Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET/CT and machine learning.

Jiahong He1, Quanshi Wang2, Yin Zhang2, Hubing Wu2, Yongsheng Zhou3, Shuangquan Zhao3.   

Abstract

PURPOSE: To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on 18F-FDG PET/CT and radiomic features using machine-learning methods.
METHODS: A total of 199 colorectal cancer patients underwent pre-therapy diagnostic 18F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting 18F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis.
RESULTS: The CRC patients were divided into a training set (n = 144) and a test set (n = 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808-0.925) and XGBoost (AUC 0.903, 95% CI 0.855-0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by 18F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all p < 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC.
CONCLUSION: In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on 18F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than 18F-FDG PET/CT in both the training and test sets.

Entities:  

Keywords:  Colorectal cancer; Machine learning; PET/CT; Radiomics; Regional LN metastasis

Year:  2021        PMID: 33738763     DOI: 10.1007/s12149-021-01605-8

Source DB:  PubMed          Journal:  Ann Nucl Med        ISSN: 0914-7187            Impact factor:   2.668


  34 in total

Review 1.  Quantitative assessment of tumor metabolism using FDG-PET imaging.

Authors:  W A Weber; M Schwaiger; N Avril
Journal:  Nucl Med Biol       Date:  2000-10       Impact factor: 2.408

2.  Colorectal cancer epidemiology: incidence, mortality, survival, and risk factors.

Authors:  Fatima A Haggar; Robin P Boushey
Journal:  Clin Colon Rectal Surg       Date:  2009-11

Review 3.  Clinically important aspects of lymph node assessment in colon cancer.

Authors:  Frances C Wright; Calvin H L Law; Scott Berry; Andrew J Smith
Journal:  J Surg Oncol       Date:  2009-03-15       Impact factor: 3.454

4.  The age of reason for FDG PET image-derived indices.

Authors:  Dimitris Visvikis; Mathieu Hatt; Florent Tixier; Catherine Cheze Le Rest
Journal:  Eur J Nucl Med Mol Imaging       Date:  2012-09-12       Impact factor: 9.236

Review 5.  Lymph node evaluation and survival after curative resection of colon cancer: systematic review.

Authors:  George J Chang; Miguel A Rodriguez-Bigas; John M Skibber; Virginia A Moyer
Journal:  J Natl Cancer Inst       Date:  2007-03-21       Impact factor: 13.506

6.  Guideline for optimization of colorectal cancer surgery and pathology.

Authors:  Andrew J Smith; David K Driman; Karen Spithoff; Amber Hunter; Robin S McLeod; Marko Simunovic; Bernard Langer
Journal:  J Surg Oncol       Date:  2010-01-01       Impact factor: 3.454

7.  Evolving role of molecular imaging with PET in detecting and characterizing heterogeneity of cancer tissue at the primary and metastatic sites, a plausible explanation for failed attempts to cure malignant disorders.

Authors:  Sandip Basu; Thomas C Kwee; Robert Gatenby; Babak Saboury; Drew A Torigian; Abass Alavi
Journal:  Eur J Nucl Med Mol Imaging       Date:  2011-06       Impact factor: 9.236

8.  Cancer statistics, 2007.

Authors:  Ahmedin Jemal; Rebecca Siegel; Elizabeth Ward; Taylor Murray; Jiaquan Xu; Michael J Thun
Journal:  CA Cancer J Clin       Date:  2007 Jan-Feb       Impact factor: 508.702

9.  Preoperative diagnosis of lymph node metastases of colorectal cancer by FDG-PET/CT.

Authors:  Yoshiyuki Tsunoda; Masaaki Ito; Hirofumi Fujii; Hiroyuki Kuwano; Norio Saito
Journal:  Jpn J Clin Oncol       Date:  2008-04-19       Impact factor: 3.019

Review 10.  Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome.

Authors:  James P B O'Connor; Chris J Rose; John C Waterton; Richard A D Carano; Geoff J M Parker; Alan Jackson
Journal:  Clin Cancer Res       Date:  2014-11-24       Impact factor: 12.531

View more
  7 in total

Review 1.  Artificial intelligence for nuclear medicine in oncology.

Authors:  Kenji Hirata; Hiroyuki Sugimori; Noriyuki Fujima; Takuya Toyonaga; Kohsuke Kudo
Journal:  Ann Nucl Med       Date:  2022-01-14       Impact factor: 2.668

2.  The value of 18F-FDG PET/CT-based radiomics in predicting perineural invasion and outcome in non-metastatic colorectal cancer.

Authors:  Jie Ma; Dong Guo; Wenjie Miao; Yangyang Wang; Lei Yan; Fengyu Wu; Chuantao Zhang; Ran Zhang; Panli Zuo; Guangjie Yang; Zhenguang Wang
Journal:  Abdom Radiol (NY)       Date:  2022-02-26

Review 3.  Radiomics in Oncological PET Imaging: A Systematic Review-Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers.

Authors:  David Morland; Elizabeth Katherine Anna Triumbari; Luca Boldrini; Roberto Gatta; Daniele Pizzuto; Salvatore Annunziata
Journal:  Diagnostics (Basel)       Date:  2022-05-27

4.  18F-FDG PET/CT-based radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer.

Authors:  Xiu-Qing Xue; Wen-Ji Yu; Xun Shi; Xiao-Liang Shao; Yue-Tao Wang
Journal:  Front Oncol       Date:  2022-08-08       Impact factor: 5.738

5.  Nomogram Predicting Lymph Node Metastasis in the Early-Stage Cervical Cancer.

Authors:  Shimin Yang; Chunli Liu; Chunbo Li; Keqin Hua
Journal:  Front Med (Lausanne)       Date:  2022-06-30

6.  Computed tomography texture analysis for the prediction of lateral pelvic lymph node metastasis of rectal cancer.

Authors:  Toshihiro Nakao; Mitsuo Shimada; Kozo Yoshikawa; Takuya Tokunaga; Masaaki Nishi; Hideya Kashihara; Chie Takasu; Yuma Wada; Toshiaki Yoshimoto
Journal:  World J Surg Oncol       Date:  2022-09-03       Impact factor: 3.253

Review 7.  Applications of Artificial Intelligence in Screening, Diagnosis, Treatment, and Prognosis of Colorectal Cancer.

Authors:  Hang Qiu; Shuhan Ding; Jianbo Liu; Liya Wang; Xiaodong Wang
Journal:  Curr Oncol       Date:  2022-03-07       Impact factor: 3.677

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.